The coffee tasted like ash, reflecting the bitter taste that had settled in his mouth. He watched the new hire, Daniel, struggle with the software. He could have made a difference. He could have helped. Instead, he’d chosen the easier path. Now, the weight of his decision pressed down on him with crushing force.

His hands shook as he reached for the mouse, his movements slow and clumsy. He kept thinking of the details, the steps, the actions, and the consequences. He had come here, but at what cost.

He left the office early, needing the fresh air. The city streets were crowded, noisy, but the feeling of isolation within him was profound. He went to the park, where children laughed, but his heart felt empty. The feeling never left him.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

This story is one of 1,000 stories generated for the emotion remorseful. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 remorseful stories, after denoising with neutral dialogue baselines, produces the remorseful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the remorseful vector is projected through the unembedding matrix.

Promoted:
S0.656
L0.580
0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285